Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23080
    Prev
    Next
    INDEX
    Explanations

    assertive statements or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing personal opinions or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Done
    -0.65
     Submission
    -0.60
    Split
    -0.59
    Bo
    -0.54
    Pokemon
    -0.54
    ':
    -0.54
    opter
    -0.54
    goo
    -0.54
     Corona
    -0.54
    \",
    -0.54
    POSITIVE LOGITS
     therefore
    1.40
     however
    1.07
     moreover
    0.98
     thus
    0.90
     furthermore
    0.85
     accordingly
    0.84
     meanwhile
    0.80
    anwhile
    0.80
     consequently
    0.79
     likewise
    0.76
    Activations Density 0.974%

    No Known Activations